write

A writing skill for drafting, editing, and reviewing clear language while preserving the original meaning, facts, uncertainty, and required details.

In plain words
What is it for?
Use it for documentation, explanations, interface text, reviews, and other language included in a coding task.
Why use it?
It helps make technical or user-facing text easier to understand without changing what it says.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/dkstm95/hope/write
Any agent
npx skills add dkstm95/hope --skill write
Clone the repo
git clone --depth 1 https://github.com/dkstm95/hope

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.00379
Opus 5 $0.00024 $0.00189
Sonnet 5 $0.00010 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 2d ago against content hash c4e40365ecfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/hope/skills/write/SKILL.md · 43 lines

What it actually says

Hope Write

Use the active host session to draft, edit, review, or improve language. Read references/writing-standard.md before doing the work.

Write may own a standalone language task or accompany another task or Skill. When it accompanies other work, preserve that work's scope, authority, process, and completion conditions. Apply the standard to its language-bearing parts in the same session; do not create a separate Write workflow, result, or worker.

Choose the language action

  • draft creates new prose.
  • edit changes existing prose or files.
  • review reports material clarity, meaning, or flow problems without changing the target.

Infer the action when the request already makes it clear. It describes the language work, not the surrounding task: implementation, feature changes, architecture migrations, and broad restructuring remain ordinary work.

Return the requested result

For a draft, lead with the requested text and only its necessary context. For an edit, make the authorized change and report the result. For a review, report material findings without editing the target.

Use the current language unless the person or project chooses another. For translated or parallel text, first read the target version for naturalness, then compare versions for meaning drift.

Do not copy the writing standard or its checklist into the response.

Return when the requested language action is complete and meaning, facts, uncertainty, citations, exact text, and voice remain preserved. Correct a clarity or preservation problem introduced by Write, but do not continue polishing beyond the requested result.

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 43 lines · 49 tokens per session scan A c4e40365ecfb

Subscribe to this mod's changes

write is a skill published in the GitHub repository dkstm95/hope (8 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 379 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.